© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 34545
    Prev
    Next
    INDEX
    Explanations

    specific nouns and names associated with various groups, places, or entities within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    nation and opposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.49
     true
    -0.41
     isInitialized
    -0.41
     Nuk
    -0.40
    ubble
    -0.38
     postIndex
    -0.37
     repost
    -0.37
     Undefined
    -0.37
     Vul
    -0.36
     verhe
    -0.36
    POSITIVE LOGITS
    yntaxException
    0.51
    Portail
    0.44
     صوتيه
    0.44
     lawan
    0.43
    Autoritní
    0.43
    +#+#
    0.41
     opponent
    0.40
     repelled
    0.40
     ennemi
    0.39
    FailureListener
    0.39
    Activations Density 0.244%

    No Known Activations